def processWebpage(self, webpage, dump_xhtml=False):
if not hasattr(webpage, 'tree'):
webpage.tree = webpage._get_parse_tree()
from copy import copy
self.remapLinks(webpage)
self.tree_processor = TreeProcessor()
#self.tree_processor.getMetaInfo(webpage)
self.tree_processor.annotateNodes(webpage)
self.tree_processor.clean(webpage)
webpage.xml = self.serializeArticle(copy(webpage.tree))
self.container.addArticle(webpage)
if dump_xhtml:
return webpage.xml
del webpage.tree
del webpage.xml
